Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/stefan-stepzero/shipkit/shipkit-plannpx skills add stefan-stepzero/shipkit --skill shipkit-plangit clone --depth 1 https://github.com/stefan-stepzero/shipkitWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00037 | $0.06519 |
| Opus 5 | $0.00018 | $0.03259 |
| Sonnet 5 | $0.00007 | $0.01304 |
| Haiku 4.5 | $0.00004 | $0.00652 |
Grade A, and why
shipkit-plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 705 lines — stays where its author put it; the contents beside it link to each section on GitHub.
shipkit-plan - Implementation Planning with Failure Mode Prevention
Purpose: Transform feature specifications into validated implementation plans that prevent common planning failures: orphaned foundations, magical steps, codebase blindness, and incomplete coverage.
When to Invoke
User triggers:
- "Plan how to build this"
- "Create implementation plan"
- "How should we implement this feature?"
- "Design the technical approach"
After:
/shipkit-spechas created specification for the feature- Feature is ready for implementation planning
Prerequisites
Check before starting:
- Spec exists:
.shipkit/specs/todo/[feature-name].jsonor.shipkit/specs/active/[feature-name].json - Stack defined:
.shipkit/stack.json(from shipkit-project-context)
UI-Heavy Feature Check:
- If spec describes significant UI/UX, check if architecture.json has UI patterns or stack.json has a frontend framework
- If neither exists, warn: "This feature has significant UI — consider running
/shipkit-engineering-definitionfirst to define UI patterns" - Do NOT block on prototyping — proceed with planning
Optional but helpful:
- Architecture decisions:
.shipkit/architecture.json - Data contracts:
.shipkit/engineering-definition.json(seecomponents[].dataContracts)
Arguments
If $ARGUMENTS is provided (e.g. /shipkit-plan recipe-sharing), use it as the spec name. Try to read .shipkit/specs/todo/$ARGUMENTS.json or .shipkit/specs/active/$ARGUMENTS.json. If found, skip spec selection and proceed to Step 1 Question 2 (Plan Detail). If not found, tell the user: "No spec found matching '$ARGUMENTS'. Available specs:" then list what exists and let them choose.
If $ARGUMENTS is empty, proceed normally from Step 1.
Process
Completion Tracking
After selecting spec and reading context, create tasks:
TaskCreate: "Read context + codebase scan (parallel agents)"TaskCreate: "Architecture anti-pattern check"TaskCreate: "Archive existing plan (if exists)"TaskCreate: "Generate plan JSON"TaskCreate: "Run 6 validation checks"TaskCreate: "Write plan to disk"
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 705 lines · 37 tokens per session scan A 0bb14f407de0
shipkit-plan is a skill published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 6,519 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
golden-rss
Use when testing the rss golden build.
omh-buzz
This is a Hermes-native buzz workflow skill.
omh-code-review
This is a Hermes-native code-review workflow skill.
redteam-api-detail-pack
Domain routing and boundary guidance for authorized API security testing, including BOLA/IDOR, authentication bypass, mass assignment, missing rate limits, and GraphQL issues. Use when a task belongs to the API testing domain and needs scope, evidence, pivot, or exit criteria.
redteam-postex-detail-pack
Domain routing and boundary guidance for authorized post-exploitation testing after initial access, including privilege escalation, persistence, lateral movement, data collection, and cleanup considerations. Use when a task belongs to the post-exploitation domain and needs scope, evidence, pivot, or exit criteria.